{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:K6PAPKSP7BXWZ6R4FKTJBNPV4G","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"b747e8e7df84b446173cdf05f5a0f0afe6feca222ffb526ef846434fd2901477","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-16T16:12:39Z","title_canon_sha256":"b6c2358125de7ebde6d682ee5b6432f61c06a09bcc15bc9cd45c5f493ff25aea"},"schema_version":"1.0","source":{"id":"2410.12896","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.12896","created_at":"2026-07-05T09:21:52Z"},{"alias_kind":"arxiv_version","alias_value":"2410.12896v1","created_at":"2026-07-05T09:21:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.12896","created_at":"2026-07-05T09:21:52Z"},{"alias_kind":"pith_short_12","alias_value":"K6PAPKSP7BXW","created_at":"2026-07-05T09:21:52Z"},{"alias_kind":"pith_short_16","alias_value":"K6PAPKSP7BXWZ6R4","created_at":"2026-07-05T09:21:52Z"},{"alias_kind":"pith_short_8","alias_value":"K6PAPKSP","created_at":"2026-07-05T09:21:52Z"}],"graph_snapshots":[{"event_id":"sha256:1486324798fdcfd0cb684996cc1eb7654badd66c214eb1c7592b69ebec38c812","target":"graph","created_at":"2026-07-05T09:21:52Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2410.12896/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The success of Large Language Models (LLMs) is inherently linked to the availability of vast, diverse, and high-quality data for training and evaluation. However, the growth rate of high-quality data is significantly outpaced by the expansion of training datasets, leading to a looming data exhaustion crisis. This underscores the urgent need to enhance data efficiency and explore new data sources. In this context, synthetic data has emerged as a promising solution. Currently, data generation primarily consists of two major approaches: data augmentation and synthesis. This paper comprehensively ","authors_text":"Chenkai Zhang, Jiahui Zhu, Ke Wang, Minjie Ren, Qingjie Liu, Qiqi Zhan, Shiwei Li, Xiaoyu Wu, Yunhong Wang, Zeming Liu, Zongye Zhang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-16T16:12:39Z","title":"A Survey on Data Synthesis and Augmentation for Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.12896","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:e3a8a125dce89403753be7af441163bbfbee61aa00eb5e5d46e589d5bc394c3c","target":"record","created_at":"2026-07-05T09:21:52Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"b747e8e7df84b446173cdf05f5a0f0afe6feca222ffb526ef846434fd2901477","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-16T16:12:39Z","title_canon_sha256":"b6c2358125de7ebde6d682ee5b6432f61c06a09bcc15bc9cd45c5f493ff25aea"},"schema_version":"1.0","source":{"id":"2410.12896","kind":"arxiv","version":1}},"canonical_sha256":"579e07aa4ff86f6cfa3c2aa690b5f5e1b9cef6cd040390acac416b2fc096dd3c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"579e07aa4ff86f6cfa3c2aa690b5f5e1b9cef6cd040390acac416b2fc096dd3c","first_computed_at":"2026-07-05T09:21:52.610450Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:21:52.610450Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Y0lCHqjGUnfvikfMRwckJ6XglmQiaB6LeDY7A3Bl8dD9tbQsZO9MkJv9Ii6eoiWzScTcZkWDYndoklCLS1vTAg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:21:52.610802Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.12896","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e3a8a125dce89403753be7af441163bbfbee61aa00eb5e5d46e589d5bc394c3c","sha256:1486324798fdcfd0cb684996cc1eb7654badd66c214eb1c7592b69ebec38c812"],"state_sha256":"713068715c9579c99bef131a4e2aa33c248d3ef55f0106ea258cf00d61088dc2"}